Generalization error bounds are essential for comprehending how well machine learning models work. In this work, we suggest a novel method, i.e., the Auxiliary Distribution Method, that leads to new upper bounds on expected generalization errors that are appropriate for supervised learning scenarios.
Secure aggregation protects the local models of the users in federated learning, by not allowing the server to obtain any information beyond the aggregate model at each iteration. Naively implementing secure aggregation fails to protect the integrity of the aggregate model in the possible presence of a malicious server forging the aggregation result, which motivates verifiable aggregation in federated learning.
We consider the problem of computing a function of n variables using noisy queries, where each query is incorrect with some fixed and known probability $p \in (0,1/2)$ . Specifically, we consider the computation of the $\textsf {OR}$ function of n bits (where queries correspond to noisy readings of the bits) and the $\textsf {MAX}$ function of n real numbers (where queries correspond to noisy pairwise comparisons).
Over the past two decades, the rise in adoption of neural networks has surged in parallel with their performance. Concurrently, we have observed the inherent fragility of these prediction models: small changes to the inputs can induce classification errors across entire datasets. In the following study, we examine perturbations constrained by the $\ell _{0}$ –norm, a potent attack model in the domains of computer vision, malware detection, and natural language processing.
Detection of sparse signals arises in many modern applications such as signal processing, bioinformatics, finance, and disease surveillance. However, in many of these applications, the data may contain sensitive personal information, which is desirable to be protected during the data analysis. In this article, we consider the problem of $(\epsilon,\delta)$ -differentially private detection of a general sparse mixture with a focus on how privacy affects the detection power.
We study the community detection problem over binary symmetric stochastic block models (SBMs) while preserving the privacy of the individual connections between the vertices.
We investigate the contraction properties of locally differentially private mechanisms. More specifically, we derive tight upper bounds on the divergence between $P{\mathsf K}$ and $Q{\mathsf K}$ output distributions of an $\varepsilon $ -LDP mechanism $\mathsf K$ in terms of a divergence between the corresponding input distributions P and Q, respectively. Our first main technical result presents a sharp upper bound on the $\chi ^{2}$ -divergence $\chi ^{2}(P{\mathsf K}\|Q{\mathsf K})$ in terms of $\chi ^{2}(P\|Q)$ and $\varepsilon $ .
There is an emerging interest in generating robust algorithmic recourse that would remain valid if the model is updated or changed even slightly. Towards finding robust algorithmic recourse (or counterfactual explanations), existing literature often assumes that the original model m and the new model M are bounded in the parameter space, i.e., $\|\text {Params}(M){-}\text {Params}(m)\|{\lt }\Delta $ . However, models can often change significantly in the parameter space with little to no change in their predictions or accuracy on the given dataset.
We consider the straggler problem in decentralized learning over a logical ring while preserving user data privacy. Especially, we extend the recently proposed framework of differential privacy (DP) amplification by decentralization by Cyffers and Bellet to include overall training latency—comprising both computation and communication latency.